Joe Mama

JoeMama123123123's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 3 days ago

StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling

Paper • 2608.15089 • Published 7 days ago • 432

upvoted a collection 3 days ago

OpenFineTrain

Collection

Very fine 55 trillion+ tokens worth of ungated huggingface datasets for LLM training across 80+ datasets. • 87 items • Updated 3 days ago • 2

upvoted a paper 18 days ago

Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistants

Paper • 2607.26611 • Published 24 days ago • 32

upvoted 4 collections 28 days ago

Pretraining data

Collection

6 items • Updated Jul 1 • 1

Perplexity

Collection

1 item • Updated Jun 23 • 1

Seed data

Collection

10 items • Updated Jul 19 • 1

Value Lockin

Collection

For Value Lock in • 5 items • Updated Jun 22 • 2

upvoted 4 papers 28 days ago

Your AI Travel Agent Would Book You a Bullfight: An Agentic Benchmark for Implicit Animal Welfare in Frontier AI Models

Paper • 2606.18142 • Published Jun 17 • 2

Do LLMs Hold Their Values? MANTA: A Multi-Turn Adversarial Benchmark for Animal Welfare Reasoning

Paper • 2605.16301 • Published Jun 3 • 1

Alignment midtraining for animals

Paper • 2604.13076 • Published Apr 22 • 1

LLMs Get Lost in Evolving User Intent

Paper • 2607.20734 • Published about 1 month ago • 25

upvoted a paper 30 days ago

Subliminal Clocks: Latent Time Modelling in Diffusion Language Models

Paper • 2607.01774 • Published Jul 20 • 39

upvoted 8 papers about 1 month ago

ConsiSpace: Learning Geometric Consistency Matters for Video Spatial Reasoning

Paper • 2607.17599 • Published Jul 20 • 2

Trajectory-aware Cross-view Geo-localization with Sequential Observations

Paper • 2607.15491 • Published Jul 16 • 8

Where Should Optimizer State Live? Tiered State Allocation for Memory-Efficient Mixture-of-Experts Training

Paper • 2607.19058 • Published Jul 21 • 7

Delineate Anything v2: A Global Foundation Model for Field Delineation

Paper • 2607.19069 • Published Jul 21 • 6

H^2SD: Hybrid Hindsight Self-Distillation

Paper • 2607.18955 • Published Jul 21 • 8

Appearance Pointers -- Multimodal Region Control of Diffusion Transformers

Paper • 2607.19344 • Published Jul 21 • 4

Masked Visual Actions for Unified World Modeling

Paper • 2607.19343 • Published Jul 21 • 9

EduPanel: A Three-Agent LLM Judge for Teaching Videos -- Reliability, Complementarity, and Human Trust Calibration

Paper • 2607.18529 • Published Jul 20 • 5